© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 219922
    Prev
    Next
    INDEX
    Explanations

    quality, representative, training

    np_acts-logits-general · gemini-2.5-flash-lite

    spaces needing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NO
    0.45
    ях
    0.44
    uah
    0.43
    itivo
    0.43
     picket
    0.43
    闊
    0.43
    поло
    0.42
    授業
    0.42
     bulldozer
    0.42
    uição
    0.41
    POSITIVE LOGITS
    ဂျ
    0.52
     Elektrokhimiya
    0.51
     آمریکا
    0.47
     fontweight
    0.47
     الداخل
    0.47
     américains
    0.46
     설정
    0.45
    Mus
    0.44
    QL
    0.44
    暱
    0.44
    Activations Density 0.000%

    No Known Activations